一种基于图像强度和颜色信息的织物编织样式智能分类方法  

A Novel Method of Intelligent Analysis of Weave Pattern Based on Intensity and Color Information of Image

作　　者：钟平[1] 辛斌杰[2] 涂新星[1] 朱小龙[1] 崔瑛[3,4] 

机构地区：[1]东华大学理学院,上海201620 [2]上海工程技术大学服装学院,上海201620 [3]上海激光技术研究所,上海200233 [4]上海市激光束精细加工重点实验室,上海200233

出　　处：《应用激光》2011年第6期502-507,共6页Applied Laser

基　　金：上海市浦江人才计划资助项目(项目编号:10PJ1404600);上海市教育委员会科研创新项目资助(项目编号:11YZ215)

摘　　要：采用图像处理技术实现对织物编织样式进行自动分类。设计一种双面织物的成像系统,对选定对称双面区域同时获取其镜像图像进行分析处理。首先对获取的图像进行滤波处理,再利用图像经、纬方向上的亮度特征信息,对织物图像进行网格自动划分,通过分析所划分的网格图像在正、反两方面对应位置的颜色信息,确定纱线的交替位置,从而确定节点位置。采用颜色和结构编码方法,对织物基本循环单元的节点进行分类,并用纱线的邻近信息对其进行完善,并最终建立一个包含节点类型和颜色信息的织物结构分类模型。提出的方法有助于对织物机构参数自动分析,并实现编织模式结构逆向重构,为织物编织样式类型建立数据库系统奠定基础。This paper proposed a new method based on image processing to classify the weave pattern of the fabric automatically. The method designed a system,which can form an image of the fabric with double sides,to obtain the mirror image in the specific symmetrically double area and to analysis.First,through filtering the obtained images,as well as using the information of brightness features in the warp and weft directions,the method can automatically mesh the image of the fabric.By analyzing the color information in the correspondingly positive and negative position,we can ascertain the alternate position of the yarn,thus to make sure the position of interlacing points.According to the method of color and structured encoding,we can classify the basic unit of the interlacing points;and this classification can be perfected by the yarn＇s information in the proximity,therefore building a model of fabric structure containing types of interlacing points and color pattern.The proposed method contributes to the automatic analyze of the fabric parameter,as well as the realization of the reverse reconstruction of weave pattern,hence to establish the foundation of database that set up the weave pattern of the fabric.

关 键 词：编织样式 双面扫描 颜色编码 结构编码 

分 类 号：TH693.63[机械工程—机械制造及自动化]